Quantifying the impact of addressing data challenges in prediction of length of stay

Abstract Background Prediction of length of stay (LOS) at admission time can provide physicians and nurses insight into the illness severity of patients and aid them in avoiding adverse events and clinical deterioration. It also assists hospitals with more effectively managing their resources and ma...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Amin Naemi, Thomas Schmidt, Marjan Mansourvar, Ali Ebrahimi, Uffe Kock Wiil
Formato:	article
Lenguaje:	EN
Publicado:	BMC 2021
Materias:	Length of stay LOS Classification Regression Machine learning Vital signs Computer applications to medicine. Medical informatics R858-859.7
Acceso en línea:	https://doaj.org/article/28a80b8dfdd84e5d8ab89f300bf51680
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:28a80b8dfdd84e5d8ab89f300bf51680
record_format	dspace
spelling	oai:doaj.org-article:28a80b8dfdd84e5d8ab89f300bf516802021-11-14T12:29:19ZQuantifying the impact of addressing data challenges in prediction of length of stay10.1186/s12911-021-01660-11472-6947https://doaj.org/article/28a80b8dfdd84e5d8ab89f300bf516802021-10-01T00:00:00Zhttps://doi.org/10.1186/s12911-021-01660-1https://doaj.org/toc/1472-6947Abstract Background Prediction of length of stay (LOS) at admission time can provide physicians and nurses insight into the illness severity of patients and aid them in avoiding adverse events and clinical deterioration. It also assists hospitals with more effectively managing their resources and manpower. Methods In this field of research, there are some important challenges, such as missing values and LOS data skewness. Moreover, various studies use a binary classification which puts a wide range of patients with different conditions into one category. To address these shortcomings, first multivariate imputation techniques are applied to fill incomplete records, then two proper resampling techniques, namely Borderline-SMOTE and SMOGN, are applied to address data skewness in the classification and regression domains, respectively. Finally, machine learning (ML) techniques including neural networks, extreme gradient boosting, random forest, support vector machine, and decision tree are implemented for both approaches to predict LOS of patients admitted to the Emergency Department of Odense University Hospital between June 2018 and April 2019. The ML models are developed based on data obtained from patients at admission time, including pulse rate, arterial blood oxygen saturation, respiratory rate, systolic blood pressure, triage category, arrival ICD-10 codes, age, and gender. Results The performance of predictive models before and after addressing missing values and data skewness is evaluated using four evaluation metrics namely receiver operating characteristic, area under the curve (AUC), R-squared score (R2), and normalized root mean square error (NRMSE). Results show that the performance of predictive models is improved on average by 15.75% for AUC, 32.19% for R2 score, and 11.32% for NRMSE after addressing the mentioned challenges. Moreover, our results indicate that there is a relationship between the missing values rate, data skewness, and illness severity of patients, so it is clinically essential to take incomplete records of patients into account and apply proper solutions for interpolation of missing values. Conclusion We propose a new method comprised of three stages: missing values imputation, data skewness handling, and building predictive models based on classification and regression approaches. Our results indicated that addressing these challenges in a proper way enhanced the performance of models significantly, which led to a more valid prediction of LOS.Amin NaemiThomas SchmidtMarjan MansourvarAli EbrahimiUffe Kock WiilBMCarticleLength of stayLOSClassificationRegressionMachine learningVital signsComputer applications to medicine. Medical informaticsR858-859.7ENBMC Medical Informatics and Decision Making, Vol 21, Iss 1, Pp 1-13 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Length of stay LOS Classification Regression Machine learning Vital signs Computer applications to medicine. Medical informatics R858-859.7
spellingShingle	Length of stay LOS Classification Regression Machine learning Vital signs Computer applications to medicine. Medical informatics R858-859.7 Amin Naemi Thomas Schmidt Marjan Mansourvar Ali Ebrahimi Uffe Kock Wiil Quantifying the impact of addressing data challenges in prediction of length of stay
description	Abstract Background Prediction of length of stay (LOS) at admission time can provide physicians and nurses insight into the illness severity of patients and aid them in avoiding adverse events and clinical deterioration. It also assists hospitals with more effectively managing their resources and manpower. Methods In this field of research, there are some important challenges, such as missing values and LOS data skewness. Moreover, various studies use a binary classification which puts a wide range of patients with different conditions into one category. To address these shortcomings, first multivariate imputation techniques are applied to fill incomplete records, then two proper resampling techniques, namely Borderline-SMOTE and SMOGN, are applied to address data skewness in the classification and regression domains, respectively. Finally, machine learning (ML) techniques including neural networks, extreme gradient boosting, random forest, support vector machine, and decision tree are implemented for both approaches to predict LOS of patients admitted to the Emergency Department of Odense University Hospital between June 2018 and April 2019. The ML models are developed based on data obtained from patients at admission time, including pulse rate, arterial blood oxygen saturation, respiratory rate, systolic blood pressure, triage category, arrival ICD-10 codes, age, and gender. Results The performance of predictive models before and after addressing missing values and data skewness is evaluated using four evaluation metrics namely receiver operating characteristic, area under the curve (AUC), R-squared score (R2), and normalized root mean square error (NRMSE). Results show that the performance of predictive models is improved on average by 15.75% for AUC, 32.19% for R2 score, and 11.32% for NRMSE after addressing the mentioned challenges. Moreover, our results indicate that there is a relationship between the missing values rate, data skewness, and illness severity of patients, so it is clinically essential to take incomplete records of patients into account and apply proper solutions for interpolation of missing values. Conclusion We propose a new method comprised of three stages: missing values imputation, data skewness handling, and building predictive models based on classification and regression approaches. Our results indicated that addressing these challenges in a proper way enhanced the performance of models significantly, which led to a more valid prediction of LOS.
format	article
author	Amin Naemi Thomas Schmidt Marjan Mansourvar Ali Ebrahimi Uffe Kock Wiil
author_facet	Amin Naemi Thomas Schmidt Marjan Mansourvar Ali Ebrahimi Uffe Kock Wiil
author_sort	Amin Naemi
title	Quantifying the impact of addressing data challenges in prediction of length of stay
title_short	Quantifying the impact of addressing data challenges in prediction of length of stay
title_full	Quantifying the impact of addressing data challenges in prediction of length of stay
title_fullStr	Quantifying the impact of addressing data challenges in prediction of length of stay
title_full_unstemmed	Quantifying the impact of addressing data challenges in prediction of length of stay
title_sort	quantifying the impact of addressing data challenges in prediction of length of stay
publisher	BMC
publishDate	2021
url	https://doaj.org/article/28a80b8dfdd84e5d8ab89f300bf51680
work_keys_str_mv	AT aminnaemi quantifyingtheimpactofaddressingdatachallengesinpredictionoflengthofstay AT thomasschmidt quantifyingtheimpactofaddressingdatachallengesinpredictionoflengthofstay AT marjanmansourvar quantifyingtheimpactofaddressingdatachallengesinpredictionoflengthofstay AT aliebrahimi quantifyingtheimpactofaddressingdatachallengesinpredictionoflengthofstay AT uffekockwiil quantifyingtheimpactofaddressingdatachallengesinpredictionoflengthofstay
_version_	1718429155563929600

Quantifying the impact of addressing data challenges in prediction of length of stay

Ejemplares similares